obfus.link
Offers 31 deterministic developer tools (obfuscators, encoders, converters, validators) on a lean, machine-payable MCP endpoint.
README
obfus.link — MCP Server
31 deterministic developer tools on a lean, machine-payable MCP endpoint.
The official MCP Registry manifest for obfus.link lives in
this repo (server.json).
- Endpoint:
https://obfus.link/mcp - Registry name:
link.obfus/utility-grid - Tools: obfuscators, encoders, converters, generators, analyzers, validators (JSON→Zod, regex-from-examples, JWT hardener, curl→fetch, AES-256 link obfuscator, hashing/encoding, and more).
Why this one
- Lean by design. Most MCP servers front-load every tool definition into your agent's context (~21k tokens here) on every turn. obfus.link advertises one search tool by default and discovers the rest on demand — ~98% less resident context. Reproduce it: obfus.link/why.
- Deterministic, not generative. A tool call returns the same correct answer, byte-identical, every time — no retries, no drift.
- Machine-payable. 50 free calls per IP, then a
402challenge an agent can complete on its own (MPP). Discovery is always free.
Add it to your agent
obfus.link is a remote (Streamable HTTP) MCP server. Most clients connect via the
mcp-remote bridge — for example, in claude_desktop_config.json:
{
"mcpServers": {
"obfus-link": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://obfus.link/mcp"]
}
}
}
Full onboarding (Cursor, SPT auth for paid use, the error contract): obfus.link/docs/mcp.
Try it without an agent
A zero-dependency, clone-and-run example (messy LLM JSON → clean, typed Zod schema in two deterministic calls) lives at subether-labs/obfus-link-demo.
Links
- Site — https://obfus.link
- Why deterministic + lean — https://obfus.link/why
- MCP docs — https://obfus.link/docs/mcp
- Pricing — https://obfus.link/pricing
A Subether Labs infrastructure project.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.